This workflow follows the Agent → HTTP Request recipe pattern — see all workflows that pair these two integrations.
The workflow JSON
Copy or download the full n8n JSON below. Paste it into a new n8n workflow, add your credentials, activate. Full import guide →
{
"meta": {
"templateCredsSetupCompleted": true
},
"nodes": [
{
"parameters": {
"fields": {
"values": [
{
"name": "phone",
"stringValue": "={{ $json.body.sender.identifier }}"
},
{
"name": "message",
"stringValue": "={{ $json.body.content }}"
},
{
"name": "contact id",
"stringValue": "={{ $json.body.conversation.contact_inbox.contact_id }}"
},
{
"name": "source id",
"stringValue": "={{ $json.body.conversation.contact_inbox.source_id }}"
}
]
},
"include": "none",
"options": {}
},
"id": "10ac54a0-4b81-46b7-9441-b8e4d0a26876",
"name": "current_customer_info",
"type": "n8n-nodes-base.set",
"typeVersion": 3.2,
"position": [
-200,
400
]
},
{
"parameters": {
"content": "## conditions\n### channels other than whatsapp / another phone\n### new customer guided reply\n### AI reply in special conditions\n### AI can reply from company data\n### Human can reply when needed\n",
"height": 245.92121982210932,
"width": 634.536213468869
},
"id": "a180da4b-172a-4a74-bc98-19de600d286d",
"name": "Sticky Note",
"type": "n8n-nodes-base.stickyNote",
"typeVersion": 1,
"position": [
-1220,
640
]
},
{
"parameters": {
"jsCode": "// Loop over input items\nfor (const item of $input.all()) {\n // Check if the 'phone ' key exists (noting the trailing space)\n if (item.json && item.json['phone ']) {\n // Extract the 'phone ' field\n const phoneField = item.json['phone '];\n\n // Use a regular expression to extract the numeric phone number\n const match = phoneField.match(/(\\d+)@s\\.whatsapp\\.net/);\n if (match) {\n // Store the extracted phone number back into the item's JSON under a new field 'extractedPhoneNumber'\n item.json.extractedPhoneNumber = match[1];\n } else {\n // Handle cases where the pattern does not match\n item.json.extractedPhoneNumber = \"No valid identifier found\";\n }\n } else {\n // Handle cases where 'phone ' key is missing\n item.json.extractedPhoneNumber = \"Required data is missing\";\n }\n}\n\n// Return the modified input items with the added 'extractedPhoneNumber' field\nreturn $input.all();\n"
},
"id": "b8d544c7-547f-4d34-97e6-52a96fa11bc0",
"name": "Code",
"type": "n8n-nodes-base.code",
"typeVersion": 2,
"position": [
180,
100
]
},
{
"parameters": {
"fields": {
"values": [
{
"name": "phone ",
"stringValue": "={{ $('Webhook').item.json.body.meta.sender.identifier }}"
}
]
},
"include": "none",
"options": {}
},
"id": "f42bfa29-6870-4154-82c9-660450497c29",
"name": "new customer",
"type": "n8n-nodes-base.set",
"typeVersion": 3.2,
"position": [
-180,
140
]
},
{
"parameters": {
"jsCode": "// Loop over input items\nfor (const item of $input.all()) {\n // Check if the 'phone' key exists\n if (item.json && item.json['phone']) {\n // Extract the 'phone' field\n const phoneField = item.json['phone'];\n\n // Use a regular expression to extract the numeric phone number\n const match = phoneField.match(/(\\d+)@s\\.whatsapp\\.net/);\n if (match) {\n // Store the extracted phone number back into the item's JSON under a new field 'extractedPhoneNumber'\n item.json.extractedPhoneNumber = match[1];\n } else {\n // Handle cases where the pattern does not match\n item.json.extractedPhoneNumber = \"No valid identifier found\";\n }\n } else {\n // Handle cases where 'phone' key is missing\n item.json.extractedPhoneNumber = \"Required data is missing\";\n }\n}\n\n// Return the modified input items with the added 'extractedPhoneNumber' field\nreturn $input.all();\n"
},
"id": "7978a7ca-857b-40fb-a210-7467509f6a3a",
"name": "Code1",
"type": "n8n-nodes-base.code",
"typeVersion": 2,
"position": [
40,
400
]
},
{
"parameters": {
"method": "POST",
"url": "https://wa.mu3lnen.com/message/sendText/UK",
"sendHeaders": true,
"headerParameters": {
"parameters": [
{
"name": "apikey",
"value": "xfgavi7o7"
}
]
},
"sendBody": true,
"specifyBody": "json",
"jsonBody": "={\n \"number\":\"{{ $json.extractedPhoneNumber }}\",\n \"options\":{\n \"delay\":1200,\n \"presence\":\"composing\",\n \"linkPreview\":false\n },\n \"textMessage\":{\n \"text\":\"custom text here\ud83d\ude09\ud83e\udd23\ud83e\udd29\ud83e\udd1d\ud83d\udc4f\ud83d\udc4d\ud83d\ude4f\"\n }\n}",
"options": {
"redirect": {
"redirect": {}
}
}
},
"id": "15af9ed6-47ce-4a87-adad-45f00c9d8fea",
"name": "send message for new customer",
"type": "n8n-nodes-base.httpRequest",
"typeVersion": 4.1,
"position": [
500,
100
]
},
{
"parameters": {
"method": "POST",
"url": "https://wa.mu3lnen.com/message/sendText/UK",
"sendHeaders": true,
"headerParameters": {
"parameters": [
{
"name": "apikey",
"value": "xfgak0d2vi7o7"
}
]
},
"sendBody": true,
"specifyBody": "json",
"jsonBody": "={\n \"number\":\"{{ $('Code1').item.json.extractedPhoneNumber }}\",\n \"options\":{\n \"delay\":1200,\n \"presence\":\"composing\",\n \"linkPreview\":false\n },\n \"textMessage\":{\n \"text\":\"{{ $json.output }}\"\n }\n}",
"options": {
"redirect": {
"redirect": {}
}
}
},
"id": "7bdebf6a-6e9f-4e16-a571-f85de89f9492",
"name": "send message for current customer",
"type": "n8n-nodes-base.httpRequest",
"typeVersion": 4.1,
"position": [
1240,
460
]
},
{
"parameters": {},
"id": "e3f437a9-c625-4ff7-afd8-63a0bbea8def",
"name": "No Operation, do nothing",
"type": "n8n-nodes-base.noOp",
"typeVersion": 1,
"position": [
-460,
560
]
},
{
"parameters": {},
"id": "1a55d186-593b-47ab-b43e-d1ed2f980063",
"name": "human reply",
"type": "n8n-nodes-base.noOp",
"typeVersion": 1,
"position": [
720,
300
]
},
{
"parameters": {
"model": "gpt-4",
"options": {}
},
"id": "57fda915-bcc7-4ee7-8259-5dc4a42faadf",
"name": "OpenAI Chat Model",
"type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
"typeVersion": 1,
"position": [
580,
740
],
"credentials": {
"openAiApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"name": "amazon_retriver",
"description": "Call this tool to get requested information about amazon products, like price, sales, revenue, best selling products ...etc",
"workflowId": "k0RweIrJQsieB6Wl"
},
"id": "c130feb1-ef31-4578-b7f4-f716d6edf0ec",
"name": "Custom n8n Workflow Tool",
"type": "@n8n/n8n-nodes-langchain.toolWorkflow",
"typeVersion": 1,
"position": [
920,
720
]
},
{
"parameters": {
"sessionIdType": "customKey",
"sessionKey": "4"
},
"id": "bc4fb39f-0cea-4c4f-8f01-ded8f9bca173",
"name": "Window Buffer Memory",
"type": "@n8n/n8n-nodes-langchain.memoryBufferWindow",
"typeVersion": 1.2,
"position": [
780,
680
]
},
{
"parameters": {
"rules": {
"values": [
{
"conditions": {
"options": {
"caseSensitive": true,
"leftValue": "",
"typeValidation": "strict"
},
"conditions": [
{
"leftValue": "={{ $json.body.event }}",
"rightValue": "=conversation_created",
"operator": {
"type": "string",
"operation": "equals"
}
}
],
"combinator": "and"
},
"renameOutput": true,
"outputKey": "new customer"
},
{
"conditions": {
"options": {
"caseSensitive": true,
"leftValue": "",
"typeValidation": "strict"
},
"conditions": [
{
"id": "8edf54ef-cf7a-4e59-936a-ca3a1d6ac8d6",
"leftValue": "={{ $json.body.event }}",
"rightValue": "message_created",
"operator": {
"type": "string",
"operation": "equals",
"name": "filter.operator.equals"
}
}
],
"combinator": "and"
},
"renameOutput": true,
"outputKey": "current customer"
},
{
"conditions": {
"options": {
"caseSensitive": true,
"leftValue": "",
"typeValidation": "strict"
},
"conditions": [
{
"id": "e0bf26f4-4696-489f-ad68-2b050c879d5c",
"leftValue": "={{ $json.body.conversation.channel }}",
"rightValue": "Channel::Api",
"operator": {
"type": "string",
"operation": "notEquals"
}
}
],
"combinator": "and"
},
"renameOutput": true,
"outputKey": "other channel"
}
]
},
"options": {}
},
"id": "9bac261a-09c6-4e4b-9b82-22f7668d96ce",
"name": "Switch",
"type": "n8n-nodes-base.switch",
"typeVersion": 3,
"position": [
-620,
340
]
},
{
"parameters": {
"mode": "expression",
"numberOutputs": 2,
"output": "={{ $json.message.toLowerCase().includes(\"ai\") }}"
},
"id": "9847ee56-5381-44bf-ae90-686ee974cef1",
"name": "Human or AI reply",
"type": "n8n-nodes-base.switch",
"typeVersion": 3,
"position": [
260,
400
]
},
{
"parameters": {
"httpMethod": "POST",
"path": "ad0678f2-a082-4575-b092-6d2eafa52106",
"options": {}
},
"id": "0fe9a366-b2ff-44ba-b000-a7c1fe41c483",
"name": "Webhook",
"type": "n8n-nodes-base.webhook",
"typeVersion": 1.1,
"position": [
-1000,
340
]
},
{
"parameters": {
"text": "={{ $json.message }}",
"options": {}
},
"id": "a3626a35-6ffd-4b63-94e5-0b7f4a11ee70",
"name": "AI Agent",
"type": "@n8n/n8n-nodes-langchain.agent",
"typeVersion": 1.2,
"position": [
740,
460
]
}
],
"connections": {
"current_customer_info": {
"main": [
[
{
"node": "Code1",
"type": "main",
"index": 0
}
]
]
},
"Code": {
"main": [
[
{
"node": "send message for new customer",
"type": "main",
"index": 0
}
]
]
},
"new customer": {
"main": [
[
{
"node": "Code",
"type": "main",
"index": 0
}
]
]
},
"Code1": {
"main": [
[
{
"node": "Human or AI reply",
"type": "main",
"index": 0
}
]
]
},
"OpenAI Chat Model": {
"ai_languageModel": [
[
{
"node": "AI Agent",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Custom n8n Workflow Tool": {
"ai_tool": [
[
{
"node": "AI Agent",
"type": "ai_tool",
"index": 0
}
]
]
},
"Window Buffer Memory": {
"ai_memory": [
[
{
"node": "AI Agent",
"type": "ai_memory",
"index": 0
}
]
]
},
"Switch": {
"main": [
[
{
"node": "new customer",
"type": "main",
"index": 0
}
],
[
{
"node": "current_customer_info",
"type": "main",
"index": 0
}
],
[
{
"node": "No Operation, do nothing",
"type": "main",
"index": 0
}
]
]
},
"Human or AI reply": {
"main": [
[
{
"node": "human reply",
"type": "main",
"index": 0
}
],
[
{
"node": "AI Agent",
"type": "main",
"index": 0
}
]
]
},
"Webhook": {
"main": [
[
{
"node": "Switch",
"type": "main",
"index": 0
}
]
]
},
"AI Agent": {
"main": [
[
{
"node": "send message for current customer",
"type": "main",
"index": 0
}
]
]
}
}
}
Credentials you'll need
Each integration node will prompt for credentials when you import. We strip credential IDs before publishing — you'll add your own.
openAiApi
Pro
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
About this workflow
N8N Chatwoot Evoltuion. Uses httpRequest, lmChatOpenAi, toolWorkflow, memoryBufferWindow. Webhook trigger; 16 nodes.
Source: https://gist.github.com/drhema/44e91851b48305331110f27f781137ea — original creator credit. Request a take-down →
Related workflows
Workflows that share integrations, category, or trigger type with this one. All free to copy and import.
🧠 Gwen – The AI Voice Marketing Agent Gwen is your intelligent voice-powered marketing assistant built in n8n. She combines the power of OpenAI, ElevenLabs, and automation workflows to handle content
Tool Workflow, Memory Buffer Window, Agent +10
Create A Branded Ai-Powered Website Chatbot. Uses memoryBufferWindow, respondToWebhook, lmChatOpenAi, toolHttpRequest. Webhook trigger; 24 nodes.
Memory Buffer Window, OpenAI Chat, Tool Http Request +6
Code Respondtowebhook. Uses memoryBufferWindow, respondToWebhook, lmChatOpenAi, toolHttpRequest. Webhook trigger; 24 nodes.
Memory Buffer Window, OpenAI Chat, Tool Http Request +6
Engage website visitors with an intelligent chat widget powered by OpenAI. This template includes: 💬 Natural conversation handling 📅 Microsoft Outlook calendar integration 📝 Lead capture and informati
Memory Buffer Window, OpenAI Chat, Tool Http Request +6
L&D_AgentsAI_ATIVO. Uses httpRequest, agent, googleCalendarTool, toolSerpApi. Webhook trigger; 93 nodes.
HTTP Request, Agent, Google Calendar Tool +9